The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Crosstabs
3.5/10Local survey workflow and statistical crosstab analysis with auditable evidence
Freebeat MCP
3.5/10Freebeat MCP server for AI music videos, effects, and media uploads.
Shabaaspay Payto
3.5/10ShaBaasPay MCP server for PayTo agreements and payment initiation in Australia.
Site Spy
3.5/10MCP server for Site Spy — lets AI agents monitor websites for changes
Honey
3.5/10Search instances across GCP, AWS, K8s, Consul & Proxmox
Marketing Content Production
3.5/10Brand-safe ad, email, product description, and social content production.
Dwai Ide Bridge
3.5/10AI Agent 与 JetBrains IDE 的桥接工具：获取光标代码上下文、诊断运行报错、执行脚本、推送 Diff 修改供开发者审批。
MCP Server
3.5/10CAI MCP server — gives AI agents a custodial wallet, @cai.com email, and vault.
Aproxproxy
3.5/10Residential proxy for AI agents via x402 — fetch, sessions, exit country
Orisha Data MCP
3.5/10MCP server for x402 paid market-data endpoints.
Index365
3.5/10Start index365 scans and read prioritized findings your coding agent can use.
Appdex
3.5/10iOS App Store revenue & download estimates with confidence labels
Agent
3.5/10Plan, validate, and build products and features with LaunchChair.
Shiplight
3.5/10An MCP server that provides browser automation
Reviewable Artifacts
3.5/10Reviewable workspace discovery and private HTML review creation via stdio MCP.
Payaion
3.5/10Agent file transfer. No API key to start; price downloads in USDC on Base.
Small Site
3.5/10Validate and publish built static websites to a public Small Site URL.
Tokeven
3.5/10Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
Af360
3.5/10Watches your local projects and sites read-only and names what would be lost.
MCP Server
3.5/10Read your ParlayX account and the prediction markets from an MCP client.
MCP Server
3.5/10Live Starknet explorer data: transactions, contracts, tokens, NFTs, staking
Agentic Recall
3.5/10Long-term memory for agentic tasks. It tells you when it doesn't know.
Searchlink Lite
3.5/10Google Search Console in your AI. Local, read-only, free and open source.
Podpdf
3.5/10Turn HTML, Markdown, URLs and saved templates into PDFs with the PodPDF API.
Page Scanner
3.5/10Capture a web page from your own Chrome as a PDF whose text is still text.
Keyslip
3.5/10Send and read one-time encrypted secrets with local encryption.
Send Email MCP
3.3/10Non functional server (yet)
Marketdata
3.3/10Real-time crypto market data
Apps Sdk Template
3.3/10Description of my MCP server
Fast MCP
3.3/10Description of my MCP server
MCP Server Template Python
3.3/10Description of my MCP server
MCP Server Template Xmcp
3.3/10Description of my MCP server
Property Search MCP
3.3/10Work in progress (for now)
Robomart
3.3/10Driverless delivery.
Conjure
3.3/10Agentic commerce.
Belavista Sampa Br
3.3/10Aqui é a Bela Vista.
Auth Token MCP Service
3.3/10Auth Token MCP Service
Auth Token MCP Traced Service
3.3/10Auth Token MCP Traced Service
Authenticated Llm Agent
3.3/10Authenticated LLM Agent
Authenticated Llm Jwt Agent
3.3/10Authenticated LLM JWT Agent
Authenticated Llm MCP Agent
3.3/10Authenticated LLM MCP Agent
Authenticated MCP Agent Aed9D5
3.3/10Authenticated MCP Agent
Authenticated Multi Llm Agent
3.3/10Authenticated Multi-LLM Agent
Claude Schema Output Agent
3.3/10Claude Schema Output Agent
Encrypted Oauth Llm Agent
3.3/10Encrypted OAuth LLM Agent
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.